Android™ Requires Chilkat v11.7.0+

Extract Tables from a PDF

See more PDF Text Extraction Examples

Demonstrates the "tables" operation, which returns the tables detected on the pages as rows and cells. Each cell has its row and column (counted from 0), its row and column span, and its text. Android™

// Important: Don't forget to include the call to System.loadLibrary
// as shown at the bottom of this code sample.
package com.test;

import android.app.Activity;
import com.chilkatsoft.*;

import android.widget.TextView;
import android.os.Bundle;

public class SimpleActivity extends Activity {

  private static final String TAG = "Chilkat";

  // Called when the activity is first created.
  @Override
  public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);

    boolean success = false;

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    //  The PDF used in this example is available at price_list.pdf

    CkPdf pdf = new CkPdf();
    success = pdf.LoadFile("qa_data/pdf/price_list.pdf");
    if (success == false) {
        Log.i(TAG, pdf.lastErrorText());
        return;
        }

    CkJsonObject json = new CkJsonObject();
    CkJsonObject jsonOut = new CkJsonObject();

    //  The "tables" operation returns the tables found on the selected pages.
    //  Tables are recognized by their drawn cell borders.
    success = pdf.ExtractText("tables",json,jsonOut);
    if (success == false) {
        Log.i(TAG, pdf.lastErrorText());
        return;
        }

    Log.i(TAG, "Number of tables: " + String.valueOf(jsonOut.IntOf("count")));

    //  Used to build each row of output.
    CkStringBuilder sbRow = new CkStringBuilder();
    int currentRow;
    int row;
    int j;
    int count_j;

    int i = 0;
    int count_i = jsonOut.SizeOfArray("tables");
    while (i < count_i) {
        jsonOut.put_I(i);
        Log.i(TAG, "Table on page " + String.valueOf(jsonOut.IntOf("tables[i].page")) + ": " + String.valueOf(jsonOut.IntOf("tables[i].rows")) + " rows x " + String.valueOf(jsonOut.IntOf("tables[i].columns"))
             + " columns, detected by " + jsonOut.stringOf("tables[i].detectedBy"));

        //  The cells are listed row by row.  Print each row as its cells separated by " | ".
        currentRow = -1;
        sbRow.SetString("");
        j = 0;
        count_j = jsonOut.SizeOfArray("tables[i].cells");
        while (j < count_j) {
            jsonOut.put_J(j);
            row = jsonOut.IntOf("tables[i].cells[j].row");
            if (row != currentRow) {
                if (currentRow >= 0) {
                    Log.i(TAG, sbRow.getAsString());
                    }

                currentRow = row;
                sbRow.SetString("  ");
                }
            else {
                sbRow.Append(" | ");
                }

            sbRow.Append(jsonOut.stringOf("tables[i].cells[j].text"));
            j = j + 1;
            }

        Log.i(TAG, sbRow.getAsString());
        i = i + 1;
        }

    //  The cells of the first table as JSON:
    jsonOut.put_EmitCompact(false);
    Log.i(TAG, jsonOut.emit());

    //  Sample output:

    //  Number of tables: 1
    //  Table on page 1: 8 rows x 5 columns, detected by ruled
    //    Code | Product | Unit | Price | In Stock
    //    HT-101 | Claw hammer, 16 oz | each | $18.00 | 24
    //    HT-102 | Adjustable wrench, 10 in | each | $14.50 | 31
    //    HT-103 | Screwdriver set, 6 piece | set | $22.00 | 12
    //    HT-104 | Tape measure, 25 ft | each | $9.75 | 40
    //    HT-105 | Utility knife | each | $6.20 | 58
    //    HT-106 | Pliers, needle nose | each | $11.00 | 19
    //    HT-107 | Hand saw, 20 in | each | $21.40 | 8
    //  {
    //    "count": 1,
    //    "tables": [
    //      {
    //        "page": 1,
    //        "detectedBy": "ruled",
    //        "rows": 8,
    //        "columns": 5,
    //        "cells": [
    //          {
    //            "row": 0,
    //            "col": 0,
    //            "rowSpan": 1,
    //            "colSpan": 1,
    //            "text": "Code"
    //          },
    //          {
    //            "row": 0,
    //            "col": 1,
    //            "rowSpan": 1,
    //            "colSpan": 1,
    //            "text": "Product"
    //          },
    //          ...
    //        ]
    //      }
    //    ],
    //    "quality": {
    //      "rating": "good",
    //      ...
    //    }
    //  }

  }

  static {
      System.loadLibrary("chilkat");

      // Note: If the incorrect library name is passed to System.loadLibrary,
      // then you will see the following error message at application startup:
      //"The application <your-application-name> has stopped unexpectedly. Please try again."
  }
}